INDEX

Explanations

author followed by colon

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

for

-1.24

 will

-1.19

fonds

-0.99

or

-0.97

 екс

-0.96

 their

-0.95

</

-0.95

 schon

-0.94

 where

-0.93

 before

-0.93

POSITIVE LOGITS

 nejen

1.21

namely

1.18

mostly

1.15

不僅

1.13

 dismal

1.12

 amazingly

1.09

えっ

1.08

 occuper

1.08

不仅

1.07

 siè

1.06

Activations Density 0.003%